Triple

T1086577
Position Surface form Disambiguated ID Type / Status
Subject HAV E24064 entity
Predicate hasPassengerTerminal P1297 FINISHED
Object Terminal 3 E25199 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Terminal 3 | Statement: [HAV, hasPassengerTerminal, Terminal 3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 3
Context triple: [HAV, hasPassengerTerminal, Terminal 3]
  • A. Terminal 3
    Terminal 3 is one of the passenger terminals at Paris Charles de Gaulle Airport, primarily serving low-cost and charter airlines.
  • B. Terminal 3 chosen
    Terminal 3 is the main international passenger terminal at José Martí International Airport in Havana, Cuba, handling most long-haul and major airline operations.
  • C. Terminal 3
    Terminal 3 is a major domestic passenger terminal at San Francisco International Airport, primarily serving United Airlines and its partners.
  • D. Terminal 3
    Terminal 3 is the main modern passenger terminal at Indira Gandhi International Airport in Delhi, handling the bulk of its international and many domestic flights.
  • E. Terminal 3
    Terminal 3 is one of the passenger terminals at Stockholm Arlanda Airport, serving regional and short-haul flights within the airport’s overall terminal complex.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a49404428c819092dcc9632f5f7b8b completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b963161081908a523c8d63871652 completed March 1, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac9971114c81909769b3ad78b95189 completed March 7, 2026, 9:32 p.m.
Created at: March 1, 2026, 7:42 p.m.